CN102456018B - A kind of interactive search method and device - Google Patents
A kind of interactive search method and device Download PDFInfo
- Publication number
- CN102456018B CN102456018B CN201010519676.3A CN201010519676A CN102456018B CN 102456018 B CN102456018 B CN 102456018B CN 201010519676 A CN201010519676 A CN 201010519676A CN 102456018 B CN102456018 B CN 102456018B
- Authority
- CN
- China
- Prior art keywords
- user
- query word
- model data
- features value
- intent features
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of interactive search method and device, belong to information retrieval field.The method comprises: the query word obtaining user's input; Determine the intent features value of query word; According to the intent features value of query word and query word, determine Search Results.This device comprises query word module, eigenwert module and search module.The interactive search mode that the present invention is exchanged with search engine by people, search engine decides Search Results according to the intention of user, instead of according to search word, determine Search Results, search engine can initiatively ask a question to user by some way, to user's prompting or selection, user is helped to determine current or follow-up intention; And the intention selected according to user is decided Search Results return to user; Search engine is being collected after the reaction of user (as behaviors such as clicking, browse) can specify user view by some way, will rearrange Search Results more on one's own initiative instead of take the mode of asking a question.
Description
Technical field
The present invention relates to information retrieval field, particularly a kind of interactive search method and device.
Background technology
Due to the development of network technology, information retrieval becomes more and more important, and in traditional technical field of information retrieval, user is by input inquiry word, and then search engine obtains Search Results according to query word.
Traditional information retrieval, search engine is searched for only by the query word of user, and search procedure is unidirectional, only has user to ask a question to search engine.Can be there is very large obstacle in user, such as, construct a good query word for user being a difficult thing according to the search intention of self in use.Secondly, query word is usually shorter and with certain ambiguity, once can not complete search mission, user needs to knock in many times new query word, and when user does not search suitable document, user needs to re-enter query word, continuous repetition said process, until search suitable document; Even if for same query word, different users has different cognitions and preference.Prior art is difficult to the real intention determining user's current queries, causes Search Results not have specific aim, and accuracy is not high yet.
Summary of the invention
Embodiments provide a kind of interactive search method, it can solve Search Results in prior art does not have specific aim, the problem that accuracy is not high yet.Described technical scheme is as follows: described method comprises:
Obtain the query word of user's input;
Determine the intent features value of described query word;
According to the intent features value of described query word and described query word, determine Search Results.
Wherein, the described intent features value determining described query word, specifically comprises: the user model data obtaining described user; According to the user model data of described user, determine the intent features value of described query word.
Wherein, the user model data of the described user of described acquisition, specifically comprise: capture user behavior information, described behavioural information comprises at least one in following information: the web data inquired about, click information and browsing information; By analyzing described behavioural information, obtain user model data.
Wherein, the user model data of the described user of described acquisition, specifically comprise: obtain the facility information that user uses; According to the characteristic of described equipment, obtain user model data.
Wherein, after the user model data of the described user of described acquisition, the method also comprises: extract socialization data, carry out text analyzing, set up conceptual relation storehouse to these socialization data; Utilize described conceptual relation storehouse, determine user model data further.
Wherein, in the intent features value according to described query word and described query word, after determining Search Results, the method also comprises: according to Search Results, asks a question; According to the reply message of described problem, determine the intent features value of described query word further; According to the intent features value of described query word and the described query word determined further, determine Search Results.
The embodiment of the present invention additionally provides a kind of interactive searching device, and this device comprises:
Query word module, for obtaining the query word of user's input;
Eigenwert module, for determining the intent features value of described query word;
Search module, for the intent features value according to described query word and described query word, determines Search Results.
Wherein, described eigenwert module, specifically comprises: model data unit, for obtaining the user model data of described user; Eigenwert subelement, according to the user model data of described user, determines the intent features value of described query word.
Wherein, described model data unit, specifically comprises: Query Information subelement, and for capturing user behavior information, described behavioural information comprises at least one in following information: the web data inquired about, click information and browsing information; First model data subelement, for analyzing described behavioural information, obtains user model data.
Wherein, described model data unit, specifically comprises: facility information subelement, for obtaining the facility information that user uses; Second model data subelement, for the characteristic according to described equipment, obtains user model data.
Wherein, described model data unit also comprises: conceptual relation storehouse subelement, for extracting socialization data, carrying out text analyzing, set up conceptual relation storehouse to these socialization data.Model data optimizes subelement, for utilizing described conceptual relation storehouse, determines user model data further.
Wherein, this device also comprises: put question to module, for according to Search Results, ask a question; Eigenwert limits module, for the reply message according to described problem, determines the intent features value of described query word further; Continue retrieval module, for according to described query word and the described intent features value determined further, determine Search Results.
The present invention, by obtaining query word, determines the query intention of this query word, and searches for according to the intent features value of query word and query word, make Search Results have more specific aim and accuracy.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of the interactive search method of the embodiment of the present invention 1;
Fig. 2 is the schematic flow sheet of the interactive search method of the embodiment of the present invention 2;
Fig. 3 is the schematic flow sheet of the interactive search method of the embodiment of the present invention 3;
Fig. 4 is the schematic diagram of the example that in an embodiment of the embodiment of the present invention 3, search engine active is asked a question to user;
Fig. 5 is the schematic diagram of the Search Results of the user 2 of the embodiment of the present invention 3;
Fig. 6 is the structural representation of the interactive searching device of the embodiment of the present invention 4;
Fig. 7 is the structural representation of the eigenwert module of the embodiment of the present invention 4;
Fig. 8 is the structural representation of the model data unit of the embodiment of the present invention 4;
Fig. 9 is another structural representation of the model data unit of the embodiment of the present invention 4;
Figure 10 is the another structural representation of the model data unit of the embodiment of the present invention 4;
Figure 11 is the another structural representation of the model data unit of the embodiment of the present invention 4;
Figure 12 is another structural representation of the interactive searching device of the embodiment of the present invention 4.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly, below in conjunction with accompanying drawing, embodiment of the present invention is described further in detail.
Embodiment 1
The embodiment of the present invention provides a kind of interactive search method.See Fig. 1, the method comprises the following steps:
101: the query word obtaining user's input;
102: the intent features value determining described query word;
103: according to the intent features value of described query word and described query word, determine Search Results.
The present embodiment, by obtaining query word, is determined the query intention of this query word, and is searched for according to the intent features value of query word and query word, make Search Results have more specific aim and accuracy.
Embodiment 2
The embodiment of the present invention provides a kind of interactive search method.See Fig. 2, the method comprises the following steps:
201: the query word obtaining user's input;
Search engine receives user input query word.
202: the user model data obtaining described user;
Described user model data are that the inquiry that can reflect this user that search engine is set up for each user is in advance inclined to, user model data can comprise following information, such as, ID (the Identify of user, mark) and this user user model data (such as, preference information), the present embodiment for convenience of description, uses form 1 below to describe user model data.
| ID | User model data |
| User 1 | Music-lover, plant fan |
| User 2 | Plant fan |
| User 3 | Computer technology fan |
Form 1
After search engine receives user input query word, by the ID of this user, the user model data of this user can be obtained.
Such as, user 1 obtains user model data for " music-lover " and " plant fan "; User 2 obtains user model data for " plant fan "; User 3 obtains user model data for " computer technology fan ".
User model data are set up in advance by search engine, by multiple method establishment user model data, the method that two kinds are set up user model data is mainly described in the present embodiment, that is, by the current and/or former Query Information of user and/or the user model data setting up described user according to user operation contextual information.Respectively said method will be described below.
(1) capture user behavior information, described behavioural information comprises at least one in following information: the web data inquired about, click information and browsing information; By analyzing described behavioural information, obtain user model data.
Below for user 1 and user 2, illustrate according to user's Query Information in the past, obtain the process of the user model data of described user:
After search engine receives the query word of user 1 input, search engine is by the identification identifier of user 1, inquire user 1 query note in the past, comprise user's inquiry that is long-term and short-term, click, the information such as to browse, these indexed pages of statistical study, such as, by the page classifications of these indexes, add up the number of times that the page of every class index is clicked, by click number of times number the page classification of index is sorted, thus obtain user model data, such as, the number of times that user 1 clicks music is higher than the number of times clicking plant, so the user model data of user 1 comprise two by number of clicks: come above be music-lover, come below be plant fan, this shows, user model data more embody a concentrated reflection of the really emerging of user, so search engine will get the model data of user 1 for " music-lover " and " plant fan ", and " music-lover " is superior to " plant fan ".
In like manner, after search engine receives the query word of user 2 input, search engine is by the identification identifier of user 2, inquire user 2 query note in the past, comprise user that is long-term and short-term to inquire about, click, to browse or by information such as the images (reflecting the transfer of user's notice) captured by camera, these indexed pages can more be embodied a concentrated reflection of user emerging really (or information of user's care), such as, search engine finds that he is plant fan, and so search engine will get the model data of user 2 for " plant fan ".
(2) by obtaining the facility information that described user uses, the user model data of described user are obtained.
Search engine obtains the IP of user 3, the information (identification identifier by user 3) such as operating system, browser, hardware device of use, these information can reflect the predisposition of user, such as, the browser that search engine obtains user 3 use is Safari (apple browser), can reflect that user 3 is interested in computer technology, search engine will obtain the model data of user 3 for " computer technology fan " thus.
Respectively describe search engine above and utilize the query note of user or the contextual information of user, obtain the user model data of this user, but the model data not limiting user obtains only by wherein a kind of mode, but can obtain in conjunction with two kinds of modes in aforesaid way.
Preferably, also by extracting socialization data, text analyzing being carried out to these socialization data, sets up conceptual relation storehouse, utilizing described conceptual relation storehouse, determine user model data further.
Socialization data are the data be extensively present on internet, as wikipedia, the Internet bookmark etc.These data are that user generates in the process using internet, can utilize socialization data from following two aspects:
A. socialization data are utilized can more accurately to determine user model data.A large amount of society's session datas defines effectively trains set, thus can improve the accuracy of user model data.Especially, by integrating the knowledge of a large number of users interbehavior and society's session data two aspect, we can build user interest analysis module accurately.
B. the relational structure between object socialization data extensively existed, as the concept relation graph in wikipedia, introduces among user interest model, makes user interest be not only separate different dimensions, and become the organic whole connected each other.
Detailed description is utilized socialization data below, determines the process of user model data further:
By extracting socialization data, text analyzing being carried out to these socialization data, sets up conceptual relation storehouse.Such as, extract by some webpage, the word (concept) of the frequency of occurrences in these webpages higher than certain threshold value (this threshold value can pre-set) is added up, conceptual relation storehouse is put into by with this word maximum certain word of number of times that is related, travel through the content in many such webpages and webpage, more perfect conceptual relation storehouse can be built.Utilize described conceptual relation storehouse, determine user model data further, below for user 1, user 3, said process is described:
By user 1 query note in the past, utilize described conceptual relation storehouse, more accurately can counting on user 1, to click the webpage number of times of music class the highest, such as, utilize the conceptual relation storehouse set up by socialization data, by the expanded range of the webpage of music class, such as, webpage containing a schoolmate is also divided in the category of the webpage of music class, thus, can find out, utilize socialization data more can obtain the model data " music-lover " of user 1 exactly higher than the rank of " plant fan ".
The information such as the IP used by user 3, the operating system of use, browser, hardware device, utilize described conceptual relation storehouse, such as, the browser that search engine obtains user 3 use is Safari (apple browser), and in described conceptual relation storehouse, also have the conceptual relation storehouse of other software, such as, employ the software of latest image memory technology, the concept that the software of this latest image memory technology is corresponding in described conceptual relation storehouse is: computer technology, establishes the user model data of user 3 thus more exactly.
Can reflect that user 3 is interested in computer technology, search engine will obtain the model data of user 3 for " computer technology fan " thus.
203: the intent features value determining described query word;
After search engine receives the query word of user's input, by the identification identifier of this user, just can obtain the user model data of this user, according to the user model data of this user, the intent features value of described query word can be obtained.
In the above example, search engine is according to the user model data " music-lover " of user 1 and " plant fan ", judge the intent features value of the query word " cordate telosma " that user 1 inputs, such as, first intention eigenwert is " song cordate telosma " and second intention eigenwert " plant cordate telosma ".
In like manner, search engine is according to the user model data " plant fan " of user 2, and judging the intent features value of the query word " cordate telosma " that user 2 inputs, such as, is " plant cordate telosma ".
Search engine is according to the user model data " computer technology fan " of user 3, and judging the intent features value of the query word " apple " that user 3 inputs, such as, is " computer technology of apple brand ".
204: according to intent features value and the described query word of described query word, determine Search Results;
Search engine is according to the intent features value of the query word " cordate telosma " of user 1, such as first intention eigenwert is " song cordate telosma ", second intention eigenwert is " plant cordate telosma " and this query word " cordate telosma ", determines that the Search Results of the query word " cordate telosma " of user 1 is the webpage of " song cordate telosma " and " plant cordate telosma ".
Search engine according to the intent features value of the query word " cordate telosma " of user 2, such as, is " plant cordate telosma " and this query word " cordate telosma ", determines that the Search Results of the query word " cordate telosma " of user 2 is the webpage of " plant cordate telosma ".
The present embodiment by determining user model data, thus determines the intent features value of query word, according to the intent features value of described query word and query word, can make the pointed and accuracy of Search Results.
Embodiment 3
Step 301-step 304 in the present embodiment is roughly the same with the step 201-step 204 in embodiment 2, does not repeat them here.
According to the intent features value of described query word and described query word, after determining Search Results, in order to accurately, the method can also comprise:
305: according to Search Results, ask a question;
See Fig. 3 and Fig. 4, if according to the intent features value of described query word and described query word, the index pages determined may include very abundant content, and search engine cannot determine the intent features value of user's query word further; Its implantation methods, purposes effect etc. is such as comprised at the Search Results of plant cordate telosma, now search engine then can provide some problem to user, as to provide the mode of option to allow user further select, according to the selection of user, further determined that the intent features value of user's query word, thus document user being searched for more be applicable to.
Step 305 can perform below in step 304, also can perform before step 304, as after the intent features value of query word as described in determining, ask a question, further select for user, search for afterwards again.
Inquire about " cordate telosma " for user 2, search engine may provide the selection such as " common kind ", " implantation methods ", " purposes effect ", " fragrance of a flower is poisonous ", " other similar plant " to user.After each selection, search engine can also guide user to go deep into topic with keeping.The problem proposed can in the page arbitrary suitable position, can be left-hand column, right-hand column, the top of search page or bottom, also can with Search Results rub assorted together with.Specifically see listing various may candidate intention on the left of Fig. 4, Fig. 4, can select for user, this result.
306: according to the reply message of described problem, determine the intent features value of described query word further, and according to the intent features value of described query word and described query word, determine Search Results.
See Fig. 5, the problem that user's 2 pairs of search engines provide is selected, namely answer has been made, such as, have selected the kind value method in the problem of left side, search engine is according to this answer, redefine the intent features value of query word, such as " the kind value method of plant cordate telosma ", according to the intent features value of this query word determined further, determines Search Results.
Search engine can also according to the determined Search Results of eigenwert determined further, continue to ask a question, and according to the answer of user, determine the intent features value of query word more further, to retrieve suitable Search Results, such as, can continue to ask a question " you want to understand that a kind of implantation methods " to user 2.
The interactive search mode that the present invention is exchanged with search engine by people, according to the user model data of this user, judge the intent features value of described query word, according to intent features value and the described query word of described query word, determine Search Results, according to described Search Results, also can initiatively ask a question, according to reply message, to determine the intent features value of described query word further, according to determining the intent features value of described query word and described query word further, determine Search Results, thus make search faster, more accurate, thus promote the operating experience of user.
Embodiment 4
The embodiment of the present invention provides a kind of interactive searching device.See Fig. 6, this device comprises: query word module 300, eigenwert module 310 and search module 320; Wherein,
Query word module 300, for obtaining the query word of user's input;
Eigenwert module 310, for determining the intent features value of described query word;
Search module 320, for the intent features value according to described query word and described query word, determines Search Results
See Fig. 7, described eigenwert module 310 specifically comprises: model data unit 3101 and eigenwert subelement 3102; Wherein,
Model data unit 3101, for obtaining the model data model data of described user;
Eigenwert subelement 3102, according to the model data of described user, determines the intent features value of described query word.
See Fig. 8, described model data unit 3101 specifically comprises:
Query Information subelement 31011, for capturing user behavior information, described behavioural information at least comprises one of the web data, click, browsing information of current and/or former inquiry;
First model data subelement 31012, for analyzing described behavioural information, obtains user model data.
See Fig. 9, described model data unit 3101 specifically comprises:
Facility information subelement 31013, for obtaining the facility information that described user uses;
Second model data subelement 31014, according to the characteristic of described equipment, obtains the user model data of described user
See Figure 10 and Figure 11, described model data unit 3101 also comprises:
Conceptual relation storehouse subelement 31015, for extracting socialization data, carrying out text analyzing to these socialization data, setting up conceptual relation storehouse;
Model data optimizes subelement 31016, for utilizing described conceptual relation storehouse, determines user model data further.
See Figure 12, this device also comprises:
Put question to module 330, for according to Search Results, ask a question;
Eigenwert limits module 340, for according to reply message, determines the intent features value of described query word further;
Trigger module 350, for the intent features value according to described query word and described query word, triggering searches module, determines Search Results further.
The device that the present embodiment provides, belongs to same design with embodiment of the method, and its specific implementation process refers to embodiment of the method, repeats no more here.
The interactive search mode that the present invention is exchanged with search engine by people, according to the user model data of this user, judge the intent features value of described query word, according to intent features value and the described query word of described query word, determine Search Results, if desired according to described Search Results, also can initiatively ask a question, according to reply message, to determine the intent features value of described query word further, according to determining the intent features value of described query word and described query word further, determine Search Results, assisting users filters and locating information, thus promote the operating experience of user, that is, search engine decides Search Results according to the intention of user, instead of according to search word, determine Search Results, search engine can initiatively ask a question to user by some way, to user's prompting or selection, user is helped to determine current or follow-up intention, and the intention selected according to user is decided Search Results return to user, search engine is being collected after the reaction of user (as behaviors such as clicking, browse) can specify user view by some way, will rearrange Search Results more on one's own initiative instead of take the mode of asking a question.
All or part of content in the technical scheme that above embodiment provides can be realized by software programming, and its software program is stored in the storage medium that can read, storage medium such as: the hard disk in computing machine, CD or floppy disk.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. an interactive search method, is characterized in that, described method comprises:
Obtain the query word of user's input;
Determine the intent features value of described query word;
According to the intent features value of described query word and described query word, determine Search Results;
According to Search Results, ask a question, wherein said problem gos deep into topic to redefine the intent features value of query word for guiding user;
According to the reply message of described problem, redefine the intent features value of described query word, the intent features value wherein redefined is different from the intent features value determined before;
According to described query word and the intent features value redefined, determine Search Results.
2. method according to claim 1, is characterized in that, the described intent features value determining described query word, specifically comprises:
Obtain the user model data of described user;
According to the user model data of described user, determine the intent features value of described query word.
3. method according to claim 2, is characterized in that, the user model data of the described user of described acquisition, specifically comprise:
Capture user behavior information, described behavioural information comprises at least one in following information: the web data inquired about, click information and browsing information;
By analyzing described behavioural information, obtain user model data.
4. method according to claim 2, is characterized in that, the user model data of the described user of described acquisition, specifically comprise:
Obtain the facility information that user uses;
According to the characteristic of described equipment, obtain user model data.
5. the method according to claim 3 or 4, is characterized in that, after the user model data of the described user of described acquisition, the method also comprises:
Extract socialization data, text analyzing is carried out to these socialization data, sets up conceptual relation storehouse;
Utilize described conceptual relation storehouse, determine user model data further.
6. an interactive searching device, is characterized in that, this device comprises:
Query word module, for obtaining the query word of user's input;
Eigenwert module, for determining the intent features value of described query word;
Search module, for the intent features value according to described query word and described query word, determines Search Results;
Put question to module, for according to Search Results, ask a question, wherein said problem gos deep into topic to redefine the intent features value of query word for guiding user;
Eigenwert limits module, and for the reply message according to described problem, redefine the intent features value of described query word, the intent features value wherein redefined is different from the intent features value determined before;
Trigger module, for according to described query word and the intent features value that redefines, triggering searches module, determines Search Results further.
7. device according to claim 6, is characterized in that, described eigenwert module, specifically comprises:
Model data unit, for obtaining the user model data of described user;
Eigenwert subelement, according to the user model data of described user, determines the intent features value of described query word.
8. device according to claim 7, is characterized in that, described model data unit, specifically comprises:
Query Information subelement, for capturing user behavior information, described behavioural information comprises at least one in following information: the web data inquired about, click information and browsing information;
First model data subelement, for by analyzing to described behavioural information, obtains user model data.
9. device according to claim 7, is characterized in that, described model data unit, specifically comprises:
Facility information subelement, for obtaining the facility information that user uses;
Second model data subelement, for the characteristic according to described equipment, obtains user model data.
10. device according to claim 7, is characterized in that, described model data unit also comprises:
Conceptual relation storehouse subelement, for extracting socialization data, carrying out text analyzing to these socialization data, setting up conceptual relation storehouse;
Model data optimizes subelement, for utilizing described conceptual relation storehouse, determines user model data further.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010519676.3A CN102456018B (en) | 2010-10-18 | 2010-10-18 | A kind of interactive search method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010519676.3A CN102456018B (en) | 2010-10-18 | 2010-10-18 | A kind of interactive search method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102456018A CN102456018A (en) | 2012-05-16 |
| CN102456018B true CN102456018B (en) | 2016-03-02 |
Family
ID=46039215
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201010519676.3A Active CN102456018B (en) | 2010-10-18 | 2010-10-18 | A kind of interactive search method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102456018B (en) |
Families Citing this family (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103167115B (en) * | 2012-05-25 | 2015-01-07 | 深圳市金立通信设备有限公司 | System and method of assisted search of mobile browser based on human brain memory characteristics |
| CN103514183B (en) * | 2012-06-19 | 2017-04-12 | 北京大学 | Information search method and system based on interactive document clustering |
| CN103914548B (en) | 2014-04-10 | 2018-01-09 | 北京百度网讯科技有限公司 | Information search method and device |
| CN103995870A (en) * | 2014-05-21 | 2014-08-20 | 百度在线网络技术（北京）有限公司 | Interactive searching method and device |
| CN103995880B (en) * | 2014-05-27 | 2019-03-12 | 百度在线网络技术（北京）有限公司 | Interactive method and device |
| CN104123351B (en) | 2014-07-09 | 2017-08-25 | 百度在线网络技术（北京）有限公司 | Interactive method and device |
| CN104063521B (en) * | 2014-07-17 | 2018-09-11 | 百度在线网络技术（北京）有限公司 | Searching service implementation method and device |
| CN105893391A (en) * | 2015-01-26 | 2016-08-24 | 阿里巴巴集团控股有限公司 | Intelligent answering method, apparatus and system, and electronic device |
| CN104699784B (en) * | 2015-03-13 | 2017-12-19 | 苏州思必驰信息科技有限公司 | A kind of data search method and device based on interactive mode input |
| CN105095357A (en) * | 2015-06-24 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Method and device for processing consultation data |
| CN106445940A (en) * | 2015-08-05 | 2017-02-22 | 阿里巴巴集团控股有限公司 | Navigation method and apparatus |
| CN105095187A (en) * | 2015-08-07 | 2015-11-25 | 广州神马移动信息科技有限公司 | Search intention identification method and device |
| CN105138671A (en) * | 2015-09-07 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Human-computer interaction guiding method and device based on artificial intelligence |
| CN105117479B (en) * | 2015-09-11 | 2020-08-25 | 北京金山安全软件有限公司 | Acquisition method and processing method of user search behavior information and electronic equipment |
| CN105224661A (en) * | 2015-09-30 | 2016-01-06 | 北京奇虎科技有限公司 | Conversational information search method and device |
| WO2017054758A1 (en) * | 2015-09-30 | 2017-04-06 | 北京奇虎科技有限公司 | Information search method and device |
| RU2632135C2 (en) | 2015-11-11 | 2017-10-02 | Общество С Ограниченной Ответственностью "Яндекс" | System and method for refining search results |
| CN105574143A (en) * | 2015-12-15 | 2016-05-11 | 北京奇虎科技有限公司 | Method and system for recommending content to user |
| CN105574174B (en) * | 2015-12-18 | 2019-11-26 | 北京奇虎科技有限公司 | Searching method and device based on Search Hints |
| CN106919589A (en) * | 2015-12-24 | 2017-07-04 | 北京奇虎科技有限公司 | Customer problem analysis method and device |
| CN105631052A (en) * | 2016-03-01 | 2016-06-01 | 北京百度网讯科技有限公司 | Artificial intelligence based retrieval method and artificial intelligence based retrieval device |
| CN106407348A (en) * | 2016-09-05 | 2017-02-15 | 北京百度网讯科技有限公司 | Query method and device based on artificial intelligence |
| CN113961690A (en) * | 2016-12-05 | 2022-01-21 | 阿里巴巴集团控股有限公司 | Man-machine conversation device and method for realizing man-machine conversation |
| US11232088B2 (en) | 2019-04-12 | 2022-01-25 | Adp, Llc | Method and system for interactive search indexing |
| CN110688558A (en) * | 2019-09-10 | 2020-01-14 | 中国平安财产保险股份有限公司 | Method and device for searching web page, electronic equipment and storage medium |
| CN111339424B (en) * | 2020-03-04 | 2021-05-14 | 北京字节跳动网络技术有限公司 | Method, device and equipment for searching based on keywords and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1758248A (en) * | 2004-10-05 | 2006-04-12 | 微软公司 | Systems, methods, and interfaces for providing personalized search and information access |
| CN101329674A (en) * | 2007-06-18 | 2008-12-24 | 北京搜狗科技发展有限公司 | System and method for providing personalized searching |
| CN101520784A (en) * | 2008-02-29 | 2009-09-02 | 富士通株式会社 | Information issuing system and information issuing method |
| CN101770520A (en) * | 2010-03-05 | 2010-07-07 | 南京邮电大学 | User interest modeling method based on user browsing behavior |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100494113B1 (en) * | 2000-08-21 | 2005-06-08 | (주)신종 | An information searching system via Web browser |
| WO2006001008A2 (en) * | 2004-06-24 | 2006-01-05 | Amir Lavi | System for facilitating search over a network |
-
2010
- 2010-10-18 CN CN201010519676.3A patent/CN102456018B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1758248A (en) * | 2004-10-05 | 2006-04-12 | 微软公司 | Systems, methods, and interfaces for providing personalized search and information access |
| CN101329674A (en) * | 2007-06-18 | 2008-12-24 | 北京搜狗科技发展有限公司 | System and method for providing personalized searching |
| CN101520784A (en) * | 2008-02-29 | 2009-09-02 | 富士通株式会社 | Information issuing system and information issuing method |
| CN101770520A (en) * | 2010-03-05 | 2010-07-07 | 南京邮电大学 | User interest modeling method based on user browsing behavior |
Non-Patent Citations (1)
| Title |
|---|
| 个性化信息检索技术综述;李树青;《情报理论与实践》;20090531(第2009年第5期);第2.1节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102456018A (en) | 2012-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102456018B (en) | A kind of interactive search method and device | |
| CN102760138B (en) | Classification method and device for user network behaviors and search method and device for user network behaviors | |
| Purves et al. | The design and implementation of SPIRIT: a spatially aware search engine for information retrieval on the Internet | |
| CN100405371C (en) | Method and system for abstracting new word | |
| CN108280114B (en) | Deep learning-based user literature reading interest analysis method | |
| CN103365839A (en) | Recommendation search method and device for search engines | |
| CN111008265A (en) | Enterprise information searching method and device | |
| CN102999625A (en) | Method for realizing semantic extension on retrieval request | |
| CN105183884A (en) | Search engine system and method based on big data technique | |
| US9971828B2 (en) | Document tagging and retrieval using per-subject dictionaries including subject-determining-power scores for entries | |
| CN110543595A (en) | in-station search system and method | |
| CN101101605A (en) | Method, device and system for searching web page and device for establishing index database | |
| CN104615627A (en) | Event public sentiment information extracting method and system based on micro-blog platform | |
| US10409866B1 (en) | Systems and methods for occupation normalization at a job aggregator | |
| CN103412958A (en) | Display method and device for searching result | |
| WO2015143263A1 (en) | Publication scope visualization and analysis | |
| JP5221664B2 (en) | Information map management system and information map management method | |
| CN103226601A (en) | Method and device for image search | |
| CN104484367A (en) | Data mining and analyzing system | |
| Basile et al. | Populating a knowledge base with object-location relations using distributional semantics | |
| CN103942204A (en) | Method and device for mining intentions | |
| Gupta et al. | Search bot: Search intention based filtering using decision tree based technique | |
| Kamath et al. | A semantic search engine for answering domain specific user queries | |
| CN109948034B (en) | Method and device for extracting page information based on filtering session | |
| US20190303464A1 (en) | Directed Data Indexing Based on Conceptual Relevance |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |